https://github.com/GMvandeVen/continual-learning

PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR, BI-R, ER, A-GEM, iCaRL, Generative Classifier) in three different scenarios.
https://github.com/GMvandeVen/continual-learning

artificial-neural-networks class-incremental-learning continual-learning deep-learning distillation domain-incremental-learning elastic-weight-consolidation generative-models gradient-episodic-memory icarl incremental-learning lifelong-learning replay replay-through-feedback task-incremental-learning variational-autoencoder

Last synced: 5 months ago
JSON representation

PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR, BI-R, ER, A-GEM, iCaRL, Generative Classifier) in three different scenarios.

• Host: GitHub
• URL: https://github.com/GMvandeVen/continual-learning
• Owner: GMvandeVen
• License: mit
• Created: 2018-09-26T19:32:16.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2024-03-21T09:19:26.000Z (about 1 year ago)
• Last Synced: 2024-11-05T03:51:42.476Z (5 months ago)
• Topics: artificial-neural-networks, class-incremental-learning, continual-learning, deep-learning, distillation, domain-incremental-learning, elastic-weight-consolidation, generative-models, gradient-episodic-memory, icarl, incremental-learning, lifelong-learning, replay, replay-through-feedback, task-incremental-learning, variational-autoencoder
• Language: Jupyter Notebook
• Homepage:
• Size: 3.14 MB
• Stars: 1,570
• Watchers: 28
• Forks: 311
• Open Issues: 3
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-machine-learning-resources - **[Code Collection - learning?style=social) (Table of Contents)
• StarryDivineSky - GMvandeVen/continual-learning - learning项目是一个基于PyTorch的持续学习方法实现库，涵盖了多种经典算法，例如XdG、EWC、SI、LwF、FROMP、DGR、BI-R、ER、A-GEM、iCaRL以及生成式分类器。该项目主要针对三种不同的持续学习场景进行研究和实验。其核心目标是让模型能够逐步学习新的任务，同时尽可能地保留之前学习到的知识，避免灾难性遗忘。项目通过实现和比较各种持续学习算法，旨在为研究人员提供一个方便的平台，以探索和改进持续学习技术。该项目提供的代码和实验结果可以帮助理解不同算法的工作原理和性能表现，从而推动持续学习领域的发展。 (其他_机器学习与深度学习)